Lab 9

Code

library(tidyverse)
library(here)
library(gt)
library(DT)
library(kableExtra)

Code

namesA <- read_csv(here::here('Week 9', 'Lab 9', 'StateNames_A.csv'))
datatable(namesA)

Code

namesAllison <- namesA |>
  filter(`Name` == 'Allison') |>
  rename(sex = Gender) |>
  select(Name, sex, State, Count) |>
  group_by(`State`, sex) |>
  summarize(total_names = sum(Count)) |>
  pivot_wider(names_from = sex, values_from = total_names, values_fill = 0)
namesAllisonF <- namesAllison |>
  select(`State`, `F`)


namesAllison |>
    knitr::kable(format = "html", 
               digits = 3, 
               col.names = 
                 c("State", 
                   "F", 
                   "M"),
               caption = "Number of Allisons in the U.S by State and Sex")

Number of Allisons in the U.S by State and Sex

State	F	M
AK	232	0
AL	1535	0
AR	1198	0
AZ	1880	0
CA	12413	0
CO	1594	0
CT	1099	0
DC	321	0
DE	294	0
FL	4455	0
GA	3257	0
HI	183	0
IA	1477	0
ID	451	0
IL	5110	0
IN	3067	0
KS	1283	0
KY	1905	20
LA	1209	0
MA	2218	0
MD	2229	0
ME	340	0
MI	4014	0
MN	2374	0
MO	2882	0
MS	817	0
MT	226	0
NC	3435	0
ND	285	0
NE	807	0
NH	412	0
NJ	3052	0
NM	399	0
NV	729	0
NY	5747	0
OH	5487	0
OK	1421	0
OR	1186	0
PA	4307	0
RI	306	0
SC	1228	0
SD	376	0
TN	2488	0
TX	10192	0
UT	1125	0
VA	3220	0
VT	135	0
WA	1956	0
WI	2367	0
WV	813	0
WY	142	0

Code

names_viz <- namesA |>
  filter(`Name` == 'Allison') |>
  rename(sex = Gender)

my_viz <- names_viz |>
  group_by(`Year`) |>
  summarize(total_names = sum(Count))

ggplot(data = my_viz, mapping = aes(x = `Year`, y = total_names)) +
  geom_line() +
  geom_point() +
  labs(y = NULL, title = "Popularity of the name 'Allison' in the U.S. by Count")

Code

allison_lm <- my_viz |>
  lm(total_names ~ Year, data = _) 
  
broom::tidy(allison_lm)

# A tibble: 2 × 5
  term        estimate std.error statistic  p.value
  <chr>          <dbl>     <dbl>     <dbl>    <dbl>
1 (Intercept)  209815.   42883.       4.89 0.000163
2 Year           -102.      21.4     -4.75 0.000217

Code

#Regression Equation
# y = 209815.052 - 101.581x

allison_lm |> 
  broom::augment() |> 
  ggplot(mapping = aes(y = .resid, x = .fitted)) +
  geom_point() +
  geom_line()

Code

# The pattern of residuals appears to have a relatively u-shaped form in the middle, with a couple of smaller curves on the edges. It is pretty hard to tell whether the residuals are scattered randomly or have a nonlinear pattern, so it could really go either way. Because there tends to be a larger u-shape in the middle of the distribution, I would say a quadratic model or another nonlinear model could fit the data better than a linear one. So there seems to be a decline in the name 'Allison' and unfortunately, according to the format of the question and the model, the name isn't as 'cool' anymore.

Code

x <- c('Allan', 'Alan', 'Allen')
alls <- as.vector(namesA$Name)

allans <- namesA |>
  filter(`Gender` == 'M', `Name` == alls[alls %in% x]) |>
  rename(sex = Gender)

my_viz2 <- allans |>
  group_by(`Year`) |>
  summarize(total_names = sum(Count))

ggplot(data = my_viz2, mapping = aes(x = `Year`, y = total_names)) +
  geom_line() +
  geom_point() +
  labs(y = NULL, title = "Popularity of the names 'Allan', 'Alan', and 'Allen' in the U.S. by Count")

Code

# 9

allans2 <- namesA |>
  rename(sex = Gender) |>
  filter(Year == 2000, Name == 'Allan' | Name == 'Alan' | Name == 'Allen', State == 'PA' | State == 'CA' ) |>
  select(Name, sex, State, Count) |>
  group_by(`Name`, `State`) |>
  summarize(total_names = sum(Count)) |>
  group_by(`State`) |>
  mutate(total_names = total_names / sum(total_names)) |>
  pivot_wider(names_from = Name, values_from = total_names, values_fill = 0)

# percentage breakdown: from CA: 66% Alan, 15% Allan, 20% Allen. from PA: 43% Alan, 10% Allan, 47% Allen. 

allans2 %>%
    knitr::kable(format = "html", 
               digits = 3, 
               col.names = 
                 c("State", 
                   "Alan", 
                   "Allan",
                   "Allen"),
               caption = "Proportion of Allans, Allens, and Alans in CA and PA") %>%
  kableExtra::kable_styling(font_size = 20) %>%
  kableExtra::kable_classic(html_font = "verdana")

Proportion of Allans, Allens, and Alans in CA and PA

State	Alan	Allan	Allen
CA	0.655	0.147	0.198
PA	0.429	0.101	0.471

Challenge 9

Part 1 - completed above Part 2 - I used the font size option for the last table from the kableExtra package. I also changed the font to verdana with the kable_classic() theming option, and added a title. Part 3 - added at beginning